© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 63085
    Prev
    Next
    INDEX
    Explanations

    Islamic/Arabic texts and figures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gead
    -0.07
     charges
    -0.07
     underlying
    -0.07
    ịch
    -0.07
     investor
    -0.07
     вов
    -0.07
     mechanic
    -0.07
     george
    -0.07
     Charges
    -0.07
     disorder
    -0.07
    POSITIVE LOGITS
    catalog
    0.11
    _catalog
    0.11
     catálogo
    0.11
    百科
    0.10
     catalogs
    0.10
    美容
    0.10
     Catalogue
    0.10
    Catalog
    0.10
    宝典
    0.10
    .catalog
    0.10
    Activations Density 0.006%

    No Known Activations